/**
 * 網(wǎng)頁操作相關類
 */
package test;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
 * @author winddack
 *
 */
public class Webpage {
  private String pageUrl;//定義需要操作的網(wǎng)頁地址
  private String pageEncode="UTF8";//定義需要操作的網(wǎng)頁的編碼
  public String getPageUrl() {
    return pageUrl;
  }
  public void setPageUrl(String pageUrl) {
    this.pageUrl = pageUrl;
  }
  public String getPageEncode() {
    return pageEncode;
  }
  public void setPageEncode(String pageEncode) {
    this.pageEncode = pageEncode;
  }
  //定義取源碼的方法
  public String getPageSource()
  {
    StringBuffer sb = new StringBuffer();
    try {
      //構建一URL對象
      URL url = new URL(pageUrl);
      //使用openStream得到一輸入流并由此構造一個BufferedReader對象
      BufferedReader in = new BufferedReader(new InputStreamReader(url.openStream(), pageEncode));
      String line;
      //讀取www資源
      while ((line = in.readLine()) != null)
      {
        sb.append(line);
      }
      in.close();
    }
    catch (Exception ex)
    {
      System.err.println(ex);
    }
    return sb.toString();
  }
  //定義一個把HTML標簽刪除過的源碼的方法
  public String getPageSourceWithoutHtml()
  {
    final String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; // 定義script的正則表達式
    final String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; // 定義style的正則表達式
    final String regEx_html = "<[^>]+>"; // 定義HTML標簽的正則表達式
    final String regEx_space = "\\s*|\t|\r|\n";//定義空格回車換行符
    String htmlStr = getPageSource();//獲取未處理過的源碼
    Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
    Matcher m_script = p_script.matcher(htmlStr);
    htmlStr = m_script.replaceAll(""); // 過濾script標簽
    Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
    Matcher m_style = p_style.matcher(htmlStr);
    htmlStr = m_style.replaceAll(""); // 過濾style標簽
    Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
    Matcher m_html = p_html.matcher(htmlStr);
    htmlStr = m_html.replaceAll(""); // 過濾html標簽
    Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE);
    Matcher m_space = p_space.matcher(htmlStr);
    htmlStr = m_space.replaceAll(""); // 過濾空格回車標簽
    htmlStr = htmlStr.trim(); // 返回文本字符串
    htmlStr = htmlStr.replaceAll("&nbsp;", "");
    htmlStr = htmlStr.substring(0, htmlStr.indexOf("。")+1);
    return htmlStr;
  }
}

Webpage page=new Webpage();
page.setPageUrl("http://www.baidu.com");
String code=page.getPageSourceWithoutHtml();
System.out.println(code);